MEGA-Bench Task - Traffic Future Prediction From Line Plot: leaderboard
The "Traffic Future Prediction From Line Plot" subtask of MEGA-Bench Task. A single task from MEGA-Bench, a large-scale multimodal evaluation suite that scores vision-language models across 500+ real-world tasks spanning perception, reasoning, OCR, charts, documents, and multi-image understanding.
Metric: Task Score (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 44 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude 3.5 Sonnet (20241022) | 83.9 | #291 |
| 2 | Gemini 2.5 Pro (Preview 03-25) | 82.4 | #123 |
| 3 | GLM-4.1V-9B (Thinking) | 78.1 | #472 (GLM-4.1V-9B) |
| 4 | Qwen 2 VL 72B | 76.4 | #460 |
| 5 | InternVL3-78B | 75 | #352 |
| 6 | Gemma 3 27B (IT) | 74 | #523 |
| 7 | GPT-4o Mini | 72.8 | #599 |
| 8 | Gemini 1.5 Flash (002) | 72.2 | #583 |
| 9 | GPT-4o | 69.2 | #343 |
| 10 | InternVL2.5-78B | 68.2 | #431 |
| 11 | Gemini 1.5 Pro (002) | 67.2 | #349 |
| 12 | Gemini 2.0 Flash (Preview) | 65.7 | #370 |
| 13 | Claude 3.5 Sonnet (20240620) | 62.1 | #299 |
| 14 | InternVL3-8B | 61.3 | #620 |
| 15 | Llama 4 Scout Base | 58.4 | #707 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-traffic-future-prediction-from-line-plot · How It Works · Data refreshed daily, snapshot 2026-10-20.